| --- |
| license: other |
| tags: |
| - controlnet |
| - text-to-image |
| - image-to-image |
| - inpainting |
| - sd-1-5 |
| - stable-diffusion |
| - sdxl |
| - stable-diffusion-xl |
| - illustrious-xl |
| - noobai-xl |
| - z-image |
| - z-image-turbo |
| - qwen-image |
| - qwen-image-2512 |
| - flux |
| - flux.1-dev |
| - diffsynth |
| - diffsynth-studio |
| - quantized |
| - int8 |
| - convrot |
| - comfyui |
| pipeline_tag: image-to-image |
| --- |
| |
| # ControlNet Models (ConvRot INT8) |
|
|
| <p align="center"> |
| <img src="https://raw.githubusercontent.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/main/icon.png" width="128"> |
| </p> |
|
|
| High-fidelity **ConvRot INT8** quantized weights for multi-condition and dedicated ControlNet models across diverse generative architectures (**SD1.5**, **Illustrious-XL / SDXL**, **SDXL 1.0**, **NoobAI-XL**, **Z-Image-Turbo**, **Qwen-Image / Qwen-Image-2512**, and **FLUX.1-dev**). |
|
|
| - **Technical Details & Quantization Framework:** [Hybrid-Sensitivity-Weighted-Quantization (HSWQ)](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization) |
| - **ComfyUI Loader for ConvRot INT8:** [ComfyUI-HSWQ-Loader-and-Tools](https://github.com/ussoewwin/ComfyUI-HSWQ-Loader-and-Tools) |
|
|
| ## 📦 Available Models |
| Sizes are decimal (1 GB = 10\^9 bytes) and exact; the `SHA256` column is the pack's own hash, so a download can be verified against it. |
|
|
| | Filename | Base Architecture | Base Model / Author | Supported Conditions | Quantization | File Size | SHA256 | License | |
| | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | |
| | `CN-anytest4_illustrious2_A_hswq_convrot_int8.safetensors` | Illustrious-XL / SDXL | [2vXpSwA7/iroiro-lora (Anytest v4 Variant A)](https://huggingface.co/2vXpSwA7/iroiro-lora) | Multi-condition (Canny, Lineart, Depth, Pose, Structure) | ConvRot INT8 | 1425.1 MB | `be9ff80b2f4895684c7114afff12220394f838179b5c82eadd8ebc46f5d82c25` | Fair AI / OpenRAIL++-M | |
| | `CN-anytest4_illustrious2_B_hswq_convrot_int8.safetensors` | Illustrious-XL / SDXL | [2vXpSwA7/iroiro-lora (Anytest v4 Variant B)](https://huggingface.co/2vXpSwA7/iroiro-lora) | Multi-condition (Canny, Lineart, Depth, Pose, Structure) | ConvRot INT8 | 1423.5 MB | `7e34dc3cc3334afa2b9fe5461131a1f61e289a83b1a11413d6c687e94b9dde6e` | Fair AI / OpenRAIL++-M | |
| | `controlnet-union-pro-max-sdxl-1.0_hswq_convrot_int8.safetensors` | SDXL 1.0 | [xinsir/controlnet-union-sdxl-1.0](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0) | OpenPose, Depth, Canny, Lineart, Anime Lineart, Scribble, Soft Edge, Normal, Segment, Tile, Inpaint | ConvRot INT8 | 1435.3 MB | `dcdf6f2037205c4a40b1f8863a91827ca3a5b55ec3261e07bb13d2dc855b47fb` | OpenRAIL++-M / Apache-2.0 | |
| | `noobaiXLControlnet_epsLineartRealistic_hswq_convrot_int8.safetensors` | NoobAI-XL / SDXL | [Eugeoter/noob-sdxl-controlnet-lineart_realistic](https://huggingface.co/Eugeoter/noob-sdxl-controlnet-lineart_realistic) | Lineart (Realistic) | ConvRot INT8 | 1420.2 MB | `86e795137dcf8d2876784eeecc2d61365c385f6caf4a5176d225ecd57fdcc914` | Fair AI Public 1.0-SD | |
| | `FLUX.1-dev-ControlNet-Union-Pro-2.0_hswq_convrot_int8.safetensors` | FLUX.1-dev | [Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0) | Canny, Depth, Pose, Blur, Gray, Soft Edge, Low Quality | ConvRot INT8 | 2710.6 MB | `fbcba3c76a221fba461c83680f682d3ff7aa813ef554c42e3a5449b981090c46` | Other / Non-Commercial | |
| | `Qwen-Image-2512-Fun-Controlnet-Union-2602_hswq_convrot_int8.safetensors` | Qwen-Image-2512 | [alibaba-pai/Qwen-Image-2512-Fun-Controlnet-Union](https://huggingface.co/alibaba-pai/Qwen-Image-2512-Fun-Controlnet-Union) | Canny, HED, Depth, Pose, MLSD, Scribble, Gray, Inpaint | ConvRot INT8 | 1758.7 MB | `5aec39a53f583bade3b7db18f38ed5a01905a0610c2ad2f9f792802178596bc4` | Apache-2.0 | |
| | `Qwen-Image-ControlNet-Inpainting_hswq_convrot_int8.safetensors` | Qwen-Image | [alibaba-pai/Qwen-Image-ControlNet-Inpainting](https://huggingface.co/alibaba-pai/Qwen-Image-ControlNet-Inpainting) | Inpainting, Image Editing | ConvRot INT8 | 2120.3 MB | `38f0ab7495029517d4b0bb4187cedcbdfa090a29f0bb50dfa5733f5076a0c451` | Apache-2.0 | |
| | `control_v11f1e_sd15_tile_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Tile, Super-Resolution, Detail Enhancing | ConvRot INT8 | 607.6 MB | `e90a2cb010ea2e180b75ccc722dff476d8617f6b474dbadcb82423a34102de60` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_canny_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Canny Edge Detection | ConvRot INT8 | 607.6 MB | `f7e20fa625863f0225d39a6c8feddbfeb77b2ba6a95dc13d4cf144c70c2bdb36` | OpenRAIL / CreativeML Open RAIL-M | |
| | `ioclab_sd15_recolor_hswq_convrot_int8.safetensors` | SD1.5 | ioclab (Civitai release; no Hub repository of this name exists) | Recolor | HSWQ ConvRot INT8 | **~579.5 MB** | ~0.69 GB (FP32) | **~16.0% Reduction** | Available | |
| | `control_v11f1p_sd15_depth_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Depth Map Guidance | ConvRot INT8 | 607.6 MB | `45086721b1ff4643a3ac50553eacc287e28d83fd7684bdc0dee7a8313cb6272b` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11e_sd15_ip2p_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Instruct Pix2Pix (Image Editing) | ConvRot INT8 | 607.6 MB | `43e0884402b1801f2fdfdf05e187a581090bbc0a679a187b7d7626133a0f94bd` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11e_sd15_shuffle_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Content Shuffle | ConvRot INT8 | 607.6 MB | `3a27828eb0373edaa57325fbcc1343b741d363c56bc2fcfba2857defe2be4db7` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_inpaint_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Inpainting | ConvRot INT8 | 607.6 MB | `53cf9c06ca727847942ddabd820399e364494d00e6ebe50a623dd9aa8b1337d1` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_instant_id_sdxl_hswq_convrot_int8.safetensors` | SDXL | [InstantX/InstantID](https://huggingface.co/InstantX/InstantID) | Identity (face) conditioning | ConvRot INT8 | 1420.2 MB | `a9ffbd849d007b969d91cadd1409757000f20f69d08b45d95f18243adff456c9` | Apache-2.0 | |
| | `instantid_diffusion_pytorch_model_hswq_convrot_int8.safetensors` | SDXL | [InstantX/InstantID](https://huggingface.co/InstantX/InstantID) | Identity (diffusers layout) | ConvRot INT8 | 1354.4 MB | `a9ffbd849d007b969d91cadd1409757000f20f69d08b45d95f18243adff456c9` | Apache-2.0 | |
| | `control_v11p_sd15_lineart_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Lineart | ConvRot INT8 | 607.6 MB | `f32407808652f74e52f8f14767173751af9d9c5d202a48bb3354ff8bc475567f` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_mlsd_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | M-LSD (line segments) | ConvRot INT8 | 607.6 MB | `1de1800ae02084c12b23a0f26b59507225874b0e0e2361854021cab552d2addc` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_normalbae_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Normal Map (BAE) | ConvRot INT8 | 607.6 MB | `04be4f6b091cf0c8c02cdb418b4f132618fb25e80f084214665d11cdd31e7797` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_openpose_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | OpenPose | ConvRot INT8 | 607.6 MB | `6cc82f9ecc3bae7912d6a61f4896ebc30b5b4db99e143c4333acb8fdcf6d1b05` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_scribble_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Scribble | ConvRot INT8 | 607.6 MB | `1d877c18b3210c6db8def2a552712ffb68ee973309146bef813b690fa1f7e01a` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_seg_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Semantic Segmentation | ConvRot INT8 | 607.6 MB | `20f11c5b30f66a53c6a9eeda741cf9305d24095f8df02637d8f0aa550f0547c0` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15_softedge_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Soft Edge (HED) | ConvRot INT8 | 607.6 MB | `609b04a9a38668fb084c447e9b0b6bc221466c09d8f83b610929be53f8acd395` | OpenRAIL / CreativeML Open RAIL-M | |
| | `control_v11p_sd15s2_lineart_anime_hswq_convrot_int8.safetensors` | SD1.5 | [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) | Lineart Anime | ConvRot INT8 | 607.6 MB | `d004154f605ebbf13d9632f80a3aa3adb3ec9ee5c530ad6c4da92a1fc60b0f51` | OpenRAIL / CreativeML Open RAIL-M | |
| | `qwen_image_canny_diffsynth_controlnet_hswq_convrot_int8.safetensors` | Qwen-Image | [modelscope/DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) | Canny Edge Detection & Structural Guidance | ConvRot INT8 | 1135.9 MB | `c2899255252b81fd64ef2fae0fbfd86e1496ba04cf10cc95fe45679120f1c996` | Apache-2.0 | |
| | `qwen_image_depth_diffsynth_controlnet_hswq_convrot_int8.safetensors` | Qwen-Image | [modelscope/DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) | Geometric Depth Map Guidance | ConvRot INT8 | 1135.9 MB | `7b82a9360169fa99524c03bcf913ce63713930174ad1fc332e553e5646bad44c` | Apache-2.0 | |
| | `qwen_image_inpaint_diffsynth_controlnet_hswq_convrot_int8.safetensors` | Qwen-Image | [modelscope/DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) | Masked Inpainting & Localized Editing | ConvRot INT8 | 1135.9 MB | `471b6affc7fcedafb9940fafd6354dd6eb5fac5705e647029c90598c407c82d3` | Apache-2.0 | |
| | `Z-Image-Turbo-Fun-Controlnet-Union-2.1-lite-2602-8steps_hswq_convrot_int8.safetensors` | Z-Image-Turbo | [alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1](https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1) | Multi-condition (Canny, Depth, Pose, Color, Scribble, Inpaint) | ConvRot INT8 | 1009.7 MB | `1dd12b2d028b12df6b2a4f93856f8ab161c1edc05125e3b1c987a1694e99dba4` | Apache-2.0 | |
| | `Z-Image-Turbo-Fun-Controlnet-Tile-2.1-lite-2601-8steps_hswq_convrot_int8.safetensors` | Z-Image-Turbo | [alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1](https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1) | Tile, Super-Resolution, Detail Enhancing | ConvRot INT8 | 1009.7 MB | `2998f83ef65903b4b6b22fb7ac270ed66f9a2443220563aa43db4188024763a8` | Apache-2.0 | |
|
|
| ## 🚀 Usage in ComfyUI |
| Install the loader extension: |
|
|
| ```bash |
| cd ComfyUI/custom_nodes |
| git clone https://github.com/ussoewwin/ComfyUI-HSWQ-Loader-and-Tools.git |
| ``` |
|
|
| Then place each file in the directory its type requires (see the table at the top): |
|
|
| - **ControlNet** files go in `ComfyUI/models/controlnet/` and load with the **HSWQ ControlNet Loader** node. |
| - **Model patch** files go in `ComfyUI/models/model_patches/` and load with the **HSWQ Model Patch Loader** node, then apply with `ZImageFunControlnet` / `QwenImageDiffsynthControlnet`. |
|
|
| ## 📜 Credits & License |
|
|
| ### Base Models & Research |
| - **Illustrious Anytest ControlNet:** [2vXpSwA7/iroiro-lora](https://huggingface.co/2vXpSwA7/iroiro-lora) by **2vXpSwA7** |
| - **NoobAI-XL ControlNet:** [Eugeoter/noob-sdxl-controlnet-lineart_realistic](https://huggingface.co/Eugeoter/noob-sdxl-controlnet-lineart_realistic) by **Eugeoter** (Fair AI Public 1.0-SD) |
| - **SDXL ControlNet Union:** [xinsir/controlnet-union-sdxl-1.0](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0) by **xinsir** |
| - **InstantID ControlNet:** [InstantX/InstantID](https://huggingface.co/InstantX/InstantID) by **InstantX** (Apache-2.0) |
| - **SD1.5 ControlNets (tile, canny, depth, ip2p, shuffle, inpaint, lineart, mlsd, normal, openpose, scribble, seg, softedge, lineart anime):** [lllyasviel/ControlNet-v1-1](https://huggingface.co/lllyasviel/ControlNet-v1-1) by **lllyasviel** (OpenRAIL) |
| - **Z-Image-Turbo ControlNet Models:** [alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1](https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1) & [aigc-apps/VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun) (Apache-2.0) |
| - **Qwen-Image ControlNet Models:** [alibaba-pai/Qwen-Image-2512-Fun-Controlnet-Union](https://huggingface.co/alibaba-pai/Qwen-Image-2512-Fun-Controlnet-Union), [alibaba-pai/Qwen-Image-ControlNet-Inpainting](https://huggingface.co/alibaba-pai/Qwen-Image-ControlNet-Inpainting) & [aigc-apps/VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun) (Apache-2.0) |
| - **Qwen-Image DiffSynth ControlNet Models:** [modelscope/DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) by **ModelScope / Alibaba Group** (Apache-2.0) |
| - **FLUX.1-dev ControlNet Union Pro 2.0:** [Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0) & [InstantX Team](https://huggingface.co/InstantX) (FLUX.1-dev Non-Commercial License) |
| - **Base Architectures:** [Illustrious-XL](https://civitai.red/models/675574/illustrious-xl), [Stability AI SD 1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5), [Stability AI SDXL 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) & [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
|
|
| --- |
|
|
| **Disclaimer:** These models are provided for optimization, workflow acceleration, and research purposes. Please adhere to the licenses and terms of the respective base models. |
|
|
| ## 📚 Detailed documentation |
|
|
| - [ControlNet ConvRot INT8 trajectory impact guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/ControlNet_ConvRot_INT8_Trajectory_Impact_Technical_Guide.md) |
| - [SD1.5 tile ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Tile_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 canny ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Canny_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 depth ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Depth_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 ip2p ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Ip2p_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 shuffle ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Shuffle_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 inpaint ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Inpaint_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [InstantID SDXL ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_InstantID_SDXL_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [InstantID diffusers layout ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_InstantID_Diffusers_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 lineart ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Lineart_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 mlsd ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Mlsd_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 normalbae ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Normalbae_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 openpose ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Openpose_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 scribble ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Scribble_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 seg ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Seg_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5 softedge ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Softedge_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [SD1.5s2 lineart_anime ControlNet guide](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/CN_SD15_Lineart_Anime_ConvRot_INT8_Impact_Technical_Guide.md) |
| - [Backdoor Audit Verdicts](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/backdoor/Backdoor_Audit_Verdicts.md) |
|
|
| ## 🔒 Security |
|
|
| **Backdoor audit.** Each file's audit status - verdict strength, weight coverage, the record behind it, |
| and the limits of what that measurement can show - is in |
| [Backdoor Audit Verdicts](https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/blob/main/md/backdoor/Backdoor_Audit_Verdicts.md). The audit code, the procedure and the raw records are in the same |
| repository. |
|
|
